Abstract
This study aimed to investigate the applicability of deep learning algorithms to (monthly) surface water quality forecasting. A comparison was made between the performance of an autoregressive integrated moving average (ARIMA) model and four deep learning models. All prediction algorithms, except for the ARIMA model working on a single variable, were tested with univariate inputs consisting of one of two dependent variables as well as multivariate inputs containing both dependent and independent variables. We found that deep learning models (6.31–18.78%, in terms of the mean absolute percentage error) showed better performance than the ARIMA model (27.32–404.54%) in univariate data sets, regardless of dependent variables. However, the accuracy of prediction was not improved for all dependent variables in the presence of other associated water quality variables. In addition, changes in the number of input variables, sliding window size (i.e., input and output time steps), and relevant variables (e.g., meteorological and discharge parameters) resulted in wide variation of the predictive accuracy of deep learning models, reaching as high as 377.97%. Therefore, a refined search identifying the optimal values on such influencing factors is recommended to achieve the best performance of any deep learning model in given multivariate data sets.
Highlights
Interest in deep learning for predictive modeling is growing from scientific community in the fields of hydrology and water resources [1,2,3]
Recent evidence suggests that a hybrid deep learning model combining more than two algorithms outperforms any standalone model which is eligible to time series prediction [9,13,14]
Water quality data were compiled on a monthly basis from January 2009 to December 2018 through the Water Environment Information System which was maintained by the National Institute of Environmental Research, Korea
Summary
Interest in deep learning for predictive modeling is growing from scientific community in the fields of hydrology and water resources [1,2,3]. This is true for those who take advantage of better performance from deep learning than its traditional counterparts such as machine learning and statistical models [1,4,5]. The study of Yan et al [15] showed that the predictive model based on three algorithms accurately described the cross-sectional water quality profiles, compared to Sustainability 2021, 13, 10690.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
